# Dosanjh Labs — https://dosanjhlabs.com
# Search engines and AI *answer/search* assistants are welcome to crawl and
# cite this site — they send readers our way. AI/ML *training & dataset*
# crawlers are reserved against: our content is TDM-reserved and may not be
# used to train models without a license. Policy: /ai-policy  ·  /ai.txt
# ---------------------------------------------------------------------------

User-agent: *
Allow: /
Disallow: /admin
Disallow: /account
Disallow: /success
Disallow: /cancel

# ── AI answer / search assistants — ALLOWED (they cite us and drive traffic) ──
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot
Allow: /

User-agent: Amzn-SearchBot
Allow: /

User-agent: Amzn-User
Allow: /

User-agent: meta-webindexer
Allow: /

User-agent: meta-externalfetcher
Allow: /

User-agent: MistralAI-Index
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: DuckAssistBot
Allow: /

# ── AI training / dataset crawlers — BLOCKED (content reserved, not for training) ──
# (Google-Extended and Applebot-Extended are training opt-out control tokens;
#  blocking them does NOT affect Googlebot / Applebot search indexing.)
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: webzio-extended
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Scrapy
Disallow: /

Sitemap: https://dosanjhlabs.com/sitemap.xml